Google Analytics doesn't report IP Address though - which is another reason to take a different root. Not knocking GA, I love it. However it isn't the right tools for this.

I suspect that the fiverr gigs use ping or something the create the mass of "unique visits". Very easy to spot.  Unless you have some fairly sophisticated tools to hand i'd imagine that any method that can deliver 5000 for $5 is going to be pretty easy to spot.

Might try it now though.  I love fiverr for testing stuff

Google Analytics isn't designed to pull the data in the way you really want to for something like this. It can be done I suppose, but it'd be hard work.

There are only so many metrics you can measure, and all are pretty easy to fake. However having the data is an easy to access form means that you can spot patterns and behaviour, which are much harder to fake.

Probably a starting point would be to measure distribution of the various metrics on the referred traffic v the general trend. If one particular C class block (or user agent, or resolution, or operating system, or whatever) appeared at a different frequency in the paid traffic that would be a good place to look deeper.

Thinking less technically for a moment though, I bet you could just implement one of the many anti click fraud systems to do most of this for you. same idea, but someone else has already done the coding. Googling for click fraud brings up a stack of ads (tempting to click them loads and set off their alarms!!).

It isn't hard to fake this at all I am afraid. Spotting it will depend on how sophisticated the person doing it is.

My personal preference would be not to use analytics as the means of counting it. Doing that you are going to be slightly limited in the metrics you have available and will always be "correcting" data and looking for problems rather than measuring more correctly and having problems spotted.

I'd have a script on page that logs that checks for a referrer and it if matches the pattern for website B creates a log record instead.

You then have the ability to set your rules. For instance if you get 2 referrals from the same IP a second apart would you count them? What about 10 per hour 24 hours a day? You can also log the exact timestamp with whatever variables you want to collect, so each click from the referring site might be recorded as:

• Time stamp
• Exact referring URL
• User agent
• IP
• Last visit (based on cookie)
• Total visits (based on cookie)
• #pages viewed (updating cookie on subsequent page views )
• and so on

Analytics doesn't give you access to the data in quite the same way. I'd definitely want to be logging it myself if the money involved is reasonable.

If you have a picture of the link profile you are trying to build (usually based on competitor analysis) then that helps guide you.

However my one guiding principal has always been to try not to be overly reliant on too few tactics.  That probably means I've missed out on some easy wins over the years. However it also means that I have sites that have been sitting at the top of their industry results for over a decade, never leaving page 1.

Mix it up. Find something that works - then find something else. No reason why articles can't be part of that, but if you are producing that content anyway then why not put some aside for guest posting? If you are researching guest posting opportunities why not see what else those sites are looking for?

I don't believe it helps as much, no. Particularly as the lowest quality end.

I think that a small part of that is algo based, but really that a lot of the article directories have been devalued as a result of algo change - so have less juice to pass.

However it's still a way to get links, with anchors you control, from a diverse range of IPs. Hard to ignore that.

Hi Gareth,

There is a pretty comprehensive list here, that also shows follow/nofollow status of links, Google PR and alexa ranking: http://www.vretoolbar.com/articles/directories.php

I'd imagine you'll find something there!

In this post-panda world the benefit from article submissions is slightly harder to reap, but it's still there. I'm favouring dealing in smaller numbers on sites where you can build more of a profile.  Plenty of those in that list.

Hope it helps.

You can get some of what you want, but most will be safely locked behind a login and therefore as difficult to access as it would be illegal! Depending on how busy the competitor site is this might be enough to get a good flavour:

Facebook : For fan numbers just check them out on facebook, which will give you an instant impression of how active they are there.  For share/like metrics you can use opensiteexplorer.org (Pro members only though I think), although that is on a per URL basis rather than sitewide.

For Twitter you can again get their follower numbers just by visiting their profile and the share data for any URL though OSE or other tools (I quite like Raven for this).

For both of the above the OSE data based on the home page and a couple of sample URLs might be enough. If you don't mind a bit of coding you can also get this data from the APIs directly.

For analytics data you can find the UA number easy enough - it is there in plain text in the source code of every page. However by itself it is not useful at all and certainly won't give you access to someone elses data.

You best bet for that is to use one of the sampling services - or better still more than one!  These use a sample of user data to give an indication of likely metrics.  Do though bear in mind that they are all wrong! Compare them with your own site data and you will see that they are all wildly inaccurate. However they are still better than a blind guess and the busier the target site the more accurate they tend to be. Some useful places to look for this are (in no particular order)

• http://www.spyfu.com/
• http://www.alexa.com/
• http://www.semrush.com/
• http://www.google.com/adplanner/

There are others, but that should get you started.

The answer probably differs from site to site.  I'd start by looking at how much you earn a month from people who land on product pages to give you an idea of the potential cost of that traffic bouncing.

I suspect that the compromise is something along the lines of redirecting to categories as you suggest.  However I would additionally be looking at all of the top entry pages that are product pages and 301ing those.  How many will depend on that value.

Also do talk to your developer.  It might not be as hard to match the old urls to the new ones as you imagine.  There are usually some fields that you can tie together and build a redirect rule from.

Another alternative to directing to the category page might be to direct to a search (it can still return a 404 if you wish).  If your URLs were KW rich you might be able to turn that in to a search so that the product still comes up.

Few options there to think about.  Good luck with it.

It sounds like it would be simple to do and I can't see any serious down side. Sounds like an easy win, even if the results would not be as good as if the links were appearing on longer standing pages.

Depending on what your existing link profile looks like, I would be careful about saturating anchor text.  If you suddenly had a huge jump in links all with exact match anchor text then it could be problematic.  If there is a risk of that opt for brand anchor - or better still vary the text.

I'd rather have a regular stream of links that last 90 days than not have them.  I know that some would have reservations about having large numbers of links not hanging around, but I don't think it would be an issue in this case.

Sounds fun.  You've got me thinking about ebay widgets now